High-spectral image classification method based on improved deep learning model

Abstract

The invention provides a high-spectral image classification method based on an improved learning model, and relates to the technical field of high-spectral images. The method comprises that one or more convolution layer and pooling layer form an extracted image characteristic alternatively, the obtained image characteristic is extracted for multiple times randomly to form different classificationmodels, the different classification models are used to carry out classification, and classification results are voted to obtain a final classification result in the principle that the minority submitto the majority, and the deep learning network model is constructed. The high-spectral image data to be classified is reconstructed, space spectrum information of high spectrum images is maintained,the sparsity of the data is increased, and thus, the high spectral image is easy to process by the classification model. The method includes fewer calculation parameters, is higher in classification accuracy, and can be used to classify natural objects in the high spectral image finely.

Description

technical field [0001] The invention relates to the technical field of hyperspectral images, in particular to a hyperspectral image classification method based on an improved deep learning model. Background technique [0002] The classification of hyperspectral images is one of the core contents of hyperspectral remote sensing technology, and it is the focus of research in the fields of remote sensing mapping and computer vision and pattern recognition. [0003] There are various algorithms used in hyperspectral image processing at home and abroad. Based on the spatial classification of spectral information, they are mainly divided into statistical model classification methods and non-parametric classification methods. Initially, the maximum likelihood classification of statistical models was the most widely used classification method in traditional remote sensing image classification, and then there were similar methods based on Mahalanobis distance, minimum distance, etc.,...

AI Technical Summary

Problems solved by technology

For example, in 2016, Shen Fei et al. proposed that the hyperspectral data be sparsely input to the convolutional neural network, which retains the spatial spectral information and is easy to model processing, but the accuracy of classification has not been significantly improved.

In 2017, Yuan Lin and others proposed to use a model combining autoencoder and convolutional neural network to classify hyperspectral data, which can automatically extract nonlinear information and increase classification accuracy, but at the same time increase the number of parameters of the model, and the model is unstable

Images